Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1844 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0006

Data Index: 8703 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0278. Min Act: -0.0006

Data Index: 1267408 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0280. Min Act: -0.0006

Data Index: 1050713 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0273. Min Act: -0.0006

Data Index: 780179 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0278. Min Act: -0.0006

Data Index: 616610 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0270. Min Act: -0.0006

Data Index: 112827 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0271. Min Act: -0.0006

Data Index: 753160 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0271. Min Act: -0.0006

Data Index: 1270861 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0265. Min Act: -0.0006

Data Index: 906505 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0006

Data Index: 68015 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0263. Min Act: -0.0006

Data Index: 724151 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0267. Min Act: -0.0006

Data Index: 573427 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1053954 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0006

Data Index: 948182 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0258. Min Act: -0.0006

Data Index: 1012005 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0258. Min Act: -0.0006

Data Index: 946002 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1175950 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0256. Min Act: -0.0006

Data Index: 739489 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1276535 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0255. Min Act: -0.0006

Data Index: 740000 (C4 (Web Text))

Max Activating Token Index: 39